Aaron Fischer
79139c0d97
The used clojure function which grabs the HTML code from the URL requires a content type for the response. If this is not set, the parser stops downloading the page and the whole script stopped scraping cover images. So, why does lovelybooks does not send a content type any more you ask? Because they moved the whole page finally to https and add a basic 302 redirect to the old http pages -- with no content type specified to save some traffic i guess. So, set all the urls to https, all works fine :)
99 lines
3.9 KiB
Clojure
99 lines
3.9 KiB
Clojure
;;; Copyright (C) 2014-2016 Aaron Fischer <mail@aaron-fischer.net>
|
|
;;;
|
|
;;; Permission is hereby granted, free of charge, to any person obtaining a copy of
|
|
;;; this software and associated documentation files (the "Software"), to deal in
|
|
;;; the Software without restriction, including without limitation the rights to
|
|
;;; use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
|
|
;;; the Software, and to permit persons to whom the Software is furnished to do so,
|
|
;;; subject to the following conditions:
|
|
;;;
|
|
;;; The above copyright notice and this permission notice shall be included in all
|
|
;;; copies or substantial portions of the Software.
|
|
;;;
|
|
;;; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
;;; IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
|
|
;;; FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
|
|
;;; COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
|
|
;;; IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
;;; CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
|
|
|
(ns buchdesmonats.core
|
|
(:gen-class)
|
|
(:require [net.cgrand.enlive-html :as html]
|
|
[clj-http.client :as http-client]
|
|
[clojure.string :as str]
|
|
[clojure.java.io :as io]
|
|
[clojure.tools.logging :as log]
|
|
[me.raynes.fs :as fs]))
|
|
|
|
(defn imgurl->bytes [lovelybooks-url]
|
|
(-> (java.net.URL. lovelybooks-url)
|
|
html/html-resource
|
|
(html/select [:div.bookcoverXXL :> :div :> :img])
|
|
first
|
|
(get-in [:attrs :src])
|
|
(http-client/get {:as :byte-array})
|
|
:body))
|
|
|
|
(defn encode-url-part [part]
|
|
(java.net.URLEncoder/encode part "UTF-8"))
|
|
|
|
(defn encode-url [url]
|
|
(let [parts (map encode-url-part (re-find #"\/autor\/([^/]+)\/([^/]+)\/?" url))
|
|
author (nth parts 1)
|
|
book-title (nth parts 2)]
|
|
(str "https://lovelybooks.de/autor/" author "/" book-title)))
|
|
|
|
(defn url->file [lovelybooks-url target-dir]
|
|
(let [[_ author title] (re-find #".\/autor\/([^\/]+)\/(.+)-([0-9]+)-.\/$" lovelybooks-url)]
|
|
(-> (str author "_" title ".jpg")
|
|
str/lower-case
|
|
(str/replace #"[^a-z0-9-_.]" "")
|
|
(#(io/file target-dir %)))))
|
|
|
|
(defn scrape-book-urls [datasource-url]
|
|
(->> (http-client/get datasource-url {:insecure? true})
|
|
:body
|
|
str/split-lines
|
|
(map #(second (re-find #"^\* .*\[.+\]\((.+)\)" %)))
|
|
(remove nil?)))
|
|
|
|
(defn scrape-book-cover [url target-dir]
|
|
(try
|
|
(let [target-file (url->file url target-dir)
|
|
encoded-url (encode-url url)
|
|
bytes (imgurl->bytes encoded-url)]
|
|
(with-open [out (io/output-stream target-file)]
|
|
(.write out bytes)))
|
|
(catch Exception e
|
|
(log/info "Problems with " url ", skip it."))))
|
|
|
|
(defn find-missing-covers [books-url target-dir]
|
|
(remove #(fs/exists? (url->file % target-dir))
|
|
(scrape-book-urls books-url)))
|
|
|
|
(html/defsnippet cover-item-model "buchdesmonats/layout.html" [:div#covers :> :div]
|
|
[link title]
|
|
[:a] (html/set-attr :href link)
|
|
[:img] (html/set-attr :src (url->file link "book-covers") :title title))
|
|
|
|
(html/deftemplate index-template "buchdesmonats/layout.html"
|
|
[cover-urls]
|
|
[:#covers] (html/content
|
|
(map #(cover-item-model % "zu Lovely Books")
|
|
cover-urls)))
|
|
|
|
(defn generate-html [book-urls target-dir]
|
|
(let [content (apply str (index-template book-urls))]
|
|
(with-open [out (io/writer (io/file "public" "index.html"))]
|
|
(.write out content))))
|
|
|
|
(defn -main [& args]
|
|
(let [datasource-url "https://git.okoyono.de/mezzomix/buch_des_monats/raw/master/README.mkd"
|
|
target-dir (io/file "public" "book-covers")]
|
|
(fs/mkdirs target-dir)
|
|
(generate-html (scrape-book-urls datasource-url) "public")
|
|
(doall (pmap #(scrape-book-cover % target-dir)
|
|
(find-missing-covers datasource-url target-dir)))
|
|
(System/exit 0)))
|